Skip to main content
Glama
danilofalcao

GLM Vision Server

by danilofalcao
OverviewSchemaRelated ServersScoreDiscussions
Python

MCP Server GLM Vision

A Model Context Protocol (MCP) server that integrates GLM-4.5V from Z.AI with Claude Code.

Features

  • Image Analysis: Analyze images using GLM-4.5V's vision capabilities

  • Local File Support: Analyze local image files or URLs

  • Configurable: Easy setup with environment variables

Related MCP server: glm-vision-mcp-server

Installation

Prerequisites

  • Python 3.10 or higher

  • GLM API key from Z.AI

  • Claude Code installed

Setup

  1. Clone or create the project directory:

    cd /path/to/your/project

  2. Create and activate virtual environment:

    python3 -m venv env
source env/bin/activate  # On Windows: env\Scripts\activate

  3. Install dependencies:

    pip install -r requirements.txt
# or with uv (recommended)
uv pip install -r requirements.txt

  4. Set up environment variables:

    cp .env.example .env
# Edit .env with your GLM API key from Z.AI

  5. Add the server to Claude Code:

    # Using uv (recommended)
uv run mcp install -e . --name "GLM Vision Server"

# Or manually add to Claude Desktop configuration:
claude mcp add-json --scope user glm-vision '{
  "type": "stdio",
  "command": "/path/to/your/project/env/bin/python",
  "args": ["/path/to/your/project/glm-vision.py"],
  "env": {"GLM_API_KEY": "your_api_key_here"}
}'

Configuration

Set these environment variables in your .env file:

Variable

Description

Default

GLM_API_KEY

Your GLM API key from Z.AI

(required)

GLM_API_BASE

GLM API base URL

https://api.z.ai/api/paas/v4

GLM_MODEL

Model name to use

glm-4.5v

Usage

Available Tools

glm-vision

Analyze an image file using GLM-4.5V's vision capabilities. Supports both local files and URLs.

Parameters:

  • image_path (required): Local file path or URL of the image to analyze

  • prompt (required): What to ask about the image

  • temperature (optional): Response randomness (0.0-1.0, default: 0.7)

  • thinking (optional): Enable thinking mode to see model's reasoning process (default: false)

  • max_tokens (optional): Maximum tokens in response (max 64K, default: 2048)

Example:

Use the glm-vison tool with:
- image_path: "/path/to/your/image.jpg"
- prompt: "Describe what you see in this image"

Testing

Test the server using the MCP Inspector:

# With uv
uv run python glm-vision.py

# Or with python
python glm-vision.py

Development

Running Tests

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Format code
black .
isort .

# Type checking
mypy glm-vision.py

Troubleshooting

  1. API Key Issues: Make sure your GLM_API_KEY is correctly set in the environment

  2. Connection Problems: Check your internet connection and API endpoint

  3. Model Errors: Verify that the model name (GLM_MODEL) is correct and available

License

MIT License - see LICENSE file for details.

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests if applicable

  5. Submit a pull request

Support

For issues related to the GLM API, contact Z.AI support. For MCP server issues, please create an issue in the repository.

Available Tools

1 tool
glm_visionC

Analyze an image file using GLM-4.5V's vision capabilities. Supports both local files and URLs.

ParametersJSON Schema
NameRequiredDescriptionDefault
image_pathYes
promptYes
temperatureNo
thinkingNo
max_tokensNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must reveal behavioral traits. Only states basic capability; omits details like permissions, network usage, latency, or size limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences, front-loaded with purpose. No wasted words, but slightly too brief given parameter count.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description lacks essential context for a 5-parameter vision tool. Agent needs parameter semantics, usage scenarios, and constraints.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%. Description does not explain any of the 5 parameters (image_path, prompt, temperature, thinking, max_tokens). Agent cannot infer how to format inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear statement of tool purpose: analyze images using GLM-4.5V vision capabilities, supporting local files and URLs. No sibling tools exist, so no differentiation needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when or when not to use this tool. Lacks context about alternative tools or edge cases (e.g., unsupported image formats).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion between tools, making disambiguation perfect.

Naming Consistency5/5

A single tool trivially follows a consistent naming pattern; consistency is not a concern here.

Tool Count4/5

The single tool is appropriate for a focused vision analysis server, though it borders on being too minimal for broader usage.

Completeness3/5

The tool covers image analysis but lacks supporting tools (e.g., listing models, checking capabilities), leaving potential gaps for agents.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/danilofalcao/mcp-server-glm-vision'

If you have feedback or need assistance with the MCP directory API, please join our Discord server